Open Wang-oss-tech opened 4 years ago
You need to change the number of classes in your config file to that contained in your data and update the number of filters in each of the Yolo layers accordingly (3 of them). All the instructions can be found here:
https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects
change [filters=255] to filters=(classes + 5)x3 in the 3 [convolutional] before each [yolo] layer, keep in mind that it only has to be the last [convolutional] before each of the [yolo] layers.
I can't seem to train it. I keep on getting this error message in my terminal. I am completely new to this, and I am just a high school student. Can anyone help me???
ERROR MESSAGE Error: l.outputs == params.inputs filters= in the [convolutional]-layer doesn't correspond to classes= or num= in [region]-layer
can somebody send me what they changed in the yolo-obj.cfg file? The .cfg file on this github page and the .cfg file on the more detailed page is different, and changing these the two lines of code instructed on this page does not seem to be enough.